I am developing the application on Android for human activity recognition. The classification results is satisfactory on other classifiers like KNN and Decision Tree. But what do you think should I implement the Convolutional Neural Network on mobile phone to recognize the activities. I am sure, it will increase the accuracy but what about the computational complexity and resource utilization?
Nafees Ahmad , If you were trying to train a model on the phone, it would be impossible for almost all the available networks. People usually train the model on a powerful machine/cloud with GPUs, then you can use it on the mobile for testing. Furthermore, some people download the trained models from internet and they use it in their apps.
Yes , because of the Deep Learning is an incredibly versatile and powerful technology, but running neural networks can be pretty demanding in terms of computational power, energy consumption, and disk space. This is usually not a problem for cloud applications, which run on servers with large hard drives and multiple GPUs.
Unfortunately, running a neural network on a mobile device isn’t that easy. In fact, even though smartphones are becoming more and more powerful, they still have limited computational power, battery life, and available disk space, especially for apps that we like to keep as light as possible. Doing so allows for faster downloads, smaller updates, and longer battery life, all of which users appreciate.
In order to perform image classification, portrait mode photography, text prediction, and dozens of other tasks, smartphones need to use tricks to run neural networks fast, accurately, and without using too much disk space.
In this article, we’ll look at a few of the most powerful techniques to enable neural networks to run in real time on mobile phones.
Refer this link getting some ideas
https://towardsdatascience.com/introduction-to-convolutional-neural-networks-cnn-with-tensorflow-57e2f4837e18
https://heartbeat.fritz.ai/how-smartphones-manage-to-handle-huge-neural-networks-269debcb243d
Bryar Shareef Agree with your point. Yes, we have the facility to train the model on the desktop, and it has high computational resource to tackle the high computational processing. So, we do not have to worry about processing on the desktop. Then, we can move our trained model on the mobile phone for real time work. Thank you for your effort. Karthika .P Thank you to you too for your response and effort.
- Badges
- Science topic
- Similar topics
- Social Psychology
- Attitude